Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1965. Min Act: -0.1700

Data Index: 2589145 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1487. Min Act: -0.1700

Data Index: 7457393 (Open Web Text)

Max Activating Token Index: 848

Text #2

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1551. Min Act: -0.1700

Data Index: 4974910 (Open Web Text)

Max Activating Token Index: 801

Text #3

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1380. Min Act: -0.1700

Data Index: 4724287 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1314. Min Act: -0.1700

Data Index: 3602801 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1188. Min Act: -0.1700

Data Index: 632532 (Open Web Text)

Max Activating Token Index: 258

Text #6

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.1018. Min Act: -0.1700

Data Index: 2030494 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0717. Min Act: -0.1700

Data Index: 8820268 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0807. Min Act: -0.1700

Data Index: 4759533 (Open Web Text)

Max Activating Token Index: 720

Text #9

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0399. Min Act: -0.1700

Data Index: 1108671 (Open Web Text)

Max Activating Token Index: 842

Text #10

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0614. Min Act: -0.1700

Data Index: 78029 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0265. Min Act: -0.1700

Data Index: 3210979 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0634. Min Act: -0.1700

Data Index: 4131239 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0794. Min Act: -0.1700

Data Index: 2860664 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0606. Min Act: -0.1700

Data Index: 5764522 (Open Web Text)

Max Activating Token Index: 734

Text #15

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0601. Min Act: -0.1700

Data Index: 6496234 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0424. Min Act: -0.1700

Data Index: 2607872 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0314. Min Act: -0.1700

Data Index: 5134198 (Open Web Text)

Max Activating Token Index: 497

Text #18

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0404. Min Act: -0.1700

Data Index: 4282523 (Open Web Text)

Max Activating Token Index: 324

Text #19

Max Range: 2.1965. Min Range: -2.1965

Max Act: 2.0296. Min Act: -0.1699

Data Index: 6452805 (Open Web Text)

Max Activating Token Index: 345